Blog
Articles about AI agent readiness, web standards, and preparing for autonomous agents.
WebMCP Is Live in ChatGPT and Codex: What Changed in August 2026
OpenAI turned on WebMCP site tools in the ChatGPT desktop browser and Codex on 25 August, three weeks after Shopify switched it on for every Liquid storefront. Three live deployments show the part nobody mentions: from the outside, you can't see any of it.
The Responsive Design Moment for AI Agents
The web is going through the same shift it went through with mobile. First separate m.dot sites, then responsive convergence. AI agent readiness is following the same arc: separate agent APIs today, one adaptive content layer tomorrow. We trace the parallels, the data, and what comes after convergence — the personal LLM layer.
Vercel's agent-browser: Why a CLI Beats MCP for Browser Automation
Vercel's agent-browser hit 22,000 GitHub stars in two months. It's a CLI, not an MCP server, and the data shows why: 94% fewer tokens, 3.5x faster execution, 100% success rate. We break down how it works, why it uses the accessibility tree, and what the 'less is more' finding means for your website.
Playwright: From Test Runner to AI Agent Interface
After Playwright overtook Cypress, Microsoft released Playwright MCP as an important browser automation option for compatible agents. We explain how getByRole and accessibility snapshots expose useful roles and names without guaranteeing complete agent navigation or task success.
How AI Agents See Your Website: The Accessibility Tree Explained
Browser agents may combine the DOM, accessibility tree, and screenshots. We explain why the accessibility tree is an important structured signal, which frameworks expose it, and how accessible websites support reliable interaction.
What Is agents.json? Advertising AI Agent Capabilities on Your Website
agents.json is the emerging complement to robots.txt - a machine-readable file that tells AI agents what your website can do. We cover the Wildcard specification, compare it to A2A, MCP, and OpenAPI, and show you how to implement it step by step.
What Is MCP? The Model Context Protocol for AI Agents
Anthropic's Model Context Protocol (MCP) connects AI assistants to external tools and data. We cover the architecture, discovery via /.well-known/mcp.json, current adoption, and how to implement it.
What Is Google's A2A Protocol? Agent-to-Agent Communication Explained
Google's Agent-to-Agent (A2A) protocol lets AI agents discover and work with each other. We cover the Agent Card, task lifecycle, A2A vs MCP, the partner ecosystem, and step-by-step implementation.
What Is WebMCP and Why Your Website Needs It
WebMCP is the W3C proposal for exposing website functionality directly to AI agents, now live in ChatGPT's desktop browser and on every Shopify Liquid storefront. Rewritten for the current spec: the declarative and imperative APIs on document.modelContext, what the browser enforces, where it runs today (including WebKit's opposition), and step-by-step implementation.
What Is AI Agent Readiness and Why Your Website Needs It
AI agents are changing how the web works. Learn what AI agent readiness means, why it matters for your website, and how to prepare for a world where autonomous agents browse, parse, and interact with your content.
Explore more
Explore the checks behind measured stable-core coverage.